On Friday 02 April 2010, Jesse Barnes wrote:
> On Thu, 1 Apr 2010 09:29:23 -0700 (PDT)
> Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
>
> >
> >
> > On Thu, 1 Apr 2010, Rafael J. Wysocki wrote:
> > >
> > > OK, I've verified that partial revert (below) is sufficient.
> >
> > Hmm. Through the DRM merge I just did, this area actually conflicted, and
> > the resolved version is now
> >
> > if ((rdev->family >= CHIP_RV380) &&
> > (!(rdev->flags & RADEON_IS_IGP))) {
> >
> > which presumably also fixes your issue?
> >
> > [ Side note: somebody in the DRM tree seems to be way too used to LISP,
> > and thinks that adding parenthesis always improves the code ;-]
> >
> > However, I do suspect that we should probably revert the quirk regardless
> > as being useless (ie it probably was related to those IGP chips that
> > apparently don't do MSI anyway).
> >
> > So the patch that reverts the quirk by Clemens (to replace it with
> > disabling MSI entirely when the AMD NB doesn't accept them) seems to be a
> > good idea regardless, since it's apparently not just about gfx. Jesse?
>
> Yeah, that sounds fine. I can include it in my next pull req or you
> can just pick it up directly.
Not exactly that one, please, it's missing a quirk for the affected system.
I've just sent a corrected version, here:
https://patchwork.kernel.org/patch/90275/
Rafael
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
